kevinjqliu commented on code in PR #1285:
URL: https://github.com/apache/iceberg-python/pull/1285#discussion_r1828029917


##########
pyiceberg/table/statistics.py:
##########
@@ -0,0 +1,41 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from typing import (
+    Dict,
+    List,
+    Optional,
+)
+
+from pydantic import Field
+
+from pyiceberg.typedef import IcebergBaseModel
+
+
+class BlobMetadata(IcebergBaseModel):
+    type: str
+    snapshot_id: int = Field(alias="snapshot-id")
+    sequence_number: int = Field(alias="sequence-number")
+    fields: List[int]
+    properties: Optional[Dict[str, str]] = None
+
+
+class StatisticsFile(IcebergBaseModel):
+    snapshot_id: int = Field(alias="snapshot-id")
+    statistics_path: str = Field(alias="statistics-path")
+    file_size_in_bytes: int = Field(alias="file-size-in-bytes")
+    file_footer_size_in_bytes: int = Field(alias="file-footer-size-in-bytes")
+    blob_metadata: List[BlobMetadata] = Field(alias="blob-metadata")

Review Comment:
   nit, missing `key_metadata`
   https://iceberg.apache.org/spec/#table-statistics



##########
pyiceberg/table/metadata.py:
##########
@@ -221,6 +222,14 @@ class TableMetadataCommonFields(IcebergBaseModel):
     There is always a main branch reference pointing to the
     current-snapshot-id even if the refs map is null."""
 
+    statistics: List[StatisticsFile] = Field(default_factory=list)

Review Comment:
   https://iceberg.apache.org/spec/#table-metadata-fields
   
   do you want to include both `statistics` and `partition-statistics`? 



##########
pyiceberg/table/update/__init__.py:
##########
@@ -477,6 +491,29 @@ def _(
     return base_metadata.model_copy(update={"default_sort_order_id": 
new_sort_order_id})
 
 
+@_apply_table_update.register(SetStatisticsUpdate)
+def _(update: SetStatisticsUpdate, base_metadata: TableMetadata, context: 
_TableMetadataUpdateContext) -> TableMetadata:
+    if update.snapshot_id != update.statistics.snapshot_id:
+        raise ValueError("Snapshot id in statistics does not match the 
snapshot id in the update")
+
+    rest_statistics = [stat for stat in base_metadata.statistics if 
stat.snapshot_id != update.snapshot_id]

Review Comment:
   nit: this can be a helper function to filter on snapshot_id



##########
pyiceberg/table/__init__.py:
##########
@@ -663,6 +666,42 @@ def update_location(self, location: str) -> Transaction:
         """
         raise NotImplementedError("Not yet implemented")
 
+    def set_statistics(self, snapshot_id: int, statistics_file: 
StatisticsFile) -> Transaction:
+        """Set the statistics for a snapshot.
+
+        Args:
+            snapshot_id: The snapshot ID to set the statistics for.
+            statistics_file: The statistics file to set.
+
+        Returns:
+            The alter table builder.
+        """
+        updates = (
+            SetStatisticsUpdate(
+                snapshot_id=snapshot_id,
+                statistics=statistics_file,
+            ),
+        )
+
+        return self._apply(updates, ())
+
+    def remove_statistics(self, snapshot_id: int) -> Transaction:
+        """Remove the statistics for a snapshot.
+
+        Args:
+            snapshot_id: The snapshot ID to remove the statistics for.
+
+        Returns:
+            The alter table builder.
+        """
+        updates = (
+            RemoveStatisticsUpdate(

Review Comment:
   do you mind linking the java implementation? do we want to remove all stats? 



##########
tests/conftest.py:
##########
@@ -918,6 +918,87 @@ def generate_snapshot(
     "refs": {"test": {"snapshot-id": 3051729675574597004, "type": "tag", 
"max-ref-age-ms": 10000000}},
 }
 
+TABLE_METADATA_V2_WITH_STATISTICS = {
+    "format-version": 2,
+    "table-uuid": "9c12d441-03fe-4693-9a96-a0705ddf69c1",
+    "location": "s3://bucket/test/location",
+    "last-sequence-number": 34,
+    "last-updated-ms": 1602638573590,
+    "last-column-id": 3,
+    "current-schema-id": 0,
+    "schemas": [
+        {
+            "type": "struct",
+            "schema-id": 0,
+            "fields": [
+                {
+                    "id": 1,
+                    "name": "x",
+                    "required": True,
+                    "type": "long",
+                }
+            ],
+        }
+    ],
+    "default-spec-id": 0,
+    "partition-specs": [{"spec-id": 0, "fields": []}],
+    "last-partition-id": 1000,
+    "default-sort-order-id": 0,
+    "sort-orders": [{"order-id": 0, "fields": []}],
+    "properties": {},
+    "current-snapshot-id": 3055729675574597004,
+    "snapshots": [
+        {
+            "snapshot-id": 3051729675574597004,
+            "timestamp-ms": 1515100955770,
+            "sequence-number": 0,
+            "summary": {"operation": "append"},
+            "manifest-list": "s3://a/b/1.avro",
+        },
+        {
+            "snapshot-id": 3055729675574597004,
+            "parent-snapshot-id": 3051729675574597004,
+            "timestamp-ms": 1555100955770,
+            "sequence-number": 1,
+            "summary": {"operation": "append"},
+            "manifest-list": "s3://a/b/2.avro",
+            "schema-id": 1,
+        },
+    ],
+    "statistics": [
+        {
+            "snapshot-id": 3051729675574597004,
+            "statistics-path": "s3://a/b/stats.puffin",
+            "file-size-in-bytes": 413,
+            "file-footer-size-in-bytes": 42,
+            "blob-metadata": [
+                {
+                    "type": "ndv",
+                    "snapshot-id": 3051729675574597004,
+                    "sequence-number": 1,
+                    "fields": [1],
+                }
+            ],
+        },
+        {
+            "snapshot-id": 3055729675574597004,
+            "statistics-path": "s3://a/b/stats.puffin",

Review Comment:
   this does file need to exist on disk?



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org

Reply via email to